NVIDIA L4 vs NVIDIA Tesla T4
We compared two Professional market GPUs: 24GB VRAM L4 and 16GB VRAM Tesla T4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L4 's Advantages
Released 4 years and 6 months late
Boost Clock has increased by 28% (2040MHz vs 1590MHz)
More VRAM (24GB vs 16GB)
4864 additional rendering cores
NVIDIA Tesla T4 's Advantages
Larger VRAM bandwidth (320.0GB/s vs 300.1GB/s)
Lower TDP (70W vs 72W)
Score
Benchmark
FP32 (float)
L4
+272%
30.29 TFLOPS
Tesla T4
8.141 TFLOPS
Graphics Card
Mar 2023
Release Date
Sep 2018
Tesla Ada(Lxx)
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
795 MHz
Base Clock
585 MHz
2040 MHz
Boost Clock
1590 MHz
1563 MHz
Memory Clock
1250 MHz
Memory
24GB
Memory Size
16GB
GDDR6
Memory Type
GDDR6
192bit
Memory Bus
256bit
300.1GB/s
Bandwidth
320.0GB/s
Render Config
-
-
-
60
SM Count
40
7424
Shading Units
2560
240
TMUs
160
80
ROPs
64
240
Tensor Cores
320
60
RT Cores
40
128 KB (per SM)
L1 Cache
64 KB (per SM)
48 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
163.2 GPixel/s
Pixel Rate
101.8 GPixel/s
489.6 GTexel/s
Texture Rate
254.4 GTexel/s
30.29 TFLOPS
FP16 (half)
65.13 TFLOPS
30.29 TFLOPS
FP32 (float)
8.141 TFLOPS
473.3 GFLOPS
FP64 (double)
254.4 GFLOPS
Board Design
72W
TDP
70W
250 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
AD104
GPU Name
TU104
AD104-???-A1
GPU Variant
TU104-895-A1
Ada Lovelace
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
35.8 billion
Transistors
13.6 billion
294 mm²
Die Size
545 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.9
CUDA
7.5
6.8
Shader Model
6.6
